Semisupervised Transfer Component Analysis for Domain Adaptation in Remote Sensing Image Classification

Matasci, Giona; Volpi, Michele; Kanevski, Mikhaïl; Bruzzone, Lorenzo; Tuia, Devis

doi:10.1109/tgrs.2014.2377785

Cited by 191 publications

(72 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This has led to the development of classification strategies combining the strengths of both approaches and the terms semi-supervised, transductive or domain adaptation [11][12][13][14] have emerged in the machine learning literature in the recent years. However, no real world operational use of these approaches has been made public.…”

Section: Introductionmentioning

confidence: 99%

Operational High Resolution Land Cover Map Production at the Country Scale Using Satellite Image Time Series

et al. 2017

View full text Add to dashboard Cite

Abstract:A detailed and accurate knowledge of land cover is crucial for many scientific and operational applications, and as such, it has been identified as an Essential Climate Variable. This accurate knowledge needs frequent updates. This paper presents a methodology for the fully automatic production of land cover maps at country scale using high resolution optical image time series which is based on supervised classification and uses existing databases as reference data for training and validation. The originality of the approach resides in the use of all available image data, a simple pre-processing step leading to a homogeneous set of acquisition dates over the whole area and the use of a supervised classifier which is robust to errors in the reference data. The produced maps have a kappa coefficient of 0.86 with 17 land cover classes. The processing is efficient, allowing a fast delivery of the maps after the acquisition of the image data, does not need expensive field surveys for model calibration and validation, nor human operators for decision making, and uses open and freely available imagery. The land cover maps are provided with a confidence map which gives information at the pixel level about the expected quality of the result.

show abstract

Section: Introductionmentioning

confidence: 99%

Operational High Resolution Land Cover Map Production at the Country Scale Using Satellite Image Time Series

et al. 2017

View full text Add to dashboard Cite

show abstract

“…21. end 22. obtain the final predicted label by a majority voting ensemble strategy using Equation (14).…”

Section: Return the Decision Functionmentioning

confidence: 99%

Supervised and Semi-Supervised Multi-View Canonical Correlation Analysis Ensemble for Heterogeneous Domain Adaptation in Remote Sensing Image Classification

et al. 2017

View full text Add to dashboard Cite

Abstract:In this paper, we present the supervised multi-view canonical correlation analysis ensemble (SMVCCAE) and its semi-supervised version (SSMVCCAE), which are novel techniques designed to address heterogeneous domain adaptation problems, i.e., situations in which the data to be processed and recognized are collected from different heterogeneous domains. Specifically, the multi-view canonical correlation analysis scheme is utilized to extract multiple correlation subspaces that are useful for joint representations for data association across domains. This scheme makes homogeneous domain adaption algorithms suitable for heterogeneous domain adaptation problems. Additionally, inspired by fusion methods such as Ensemble Learning (EL), this work proposes a weighted voting scheme based on canonical correlation coefficients to combine classification results in multiple correlation subspaces. Finally, the semi-supervised MVCCAE extends the original procedure by incorporating multiple speed-up spectral regression kernel discriminant analysis (SRKDA). To validate the performances of the proposed supervised procedure, a single-view canonical analysis (SVCCA) with the same base classifier (Random Forests) is used. Similarly, to evaluate the performance of the semi-supervised approach, a comparison is made with other techniques such as Logistic label propagation (LLP) and the Laplacian support vector machine (LapSVM). All of the approaches are tested on two real hyperspectral images, which are considered the target domain, with a classifier trained from synthetic low-dimensional multispectral images, which are considered the original source domain. The experimental results confirm that multi-view canonical correlation can overcome the limitations of SVCCA. Both of the proposed procedures outperform the ones used in the comparison with respect to not only the classification accuracy but also the computational efficiency. Moreover, this research shows that canonical correlation weighted voting (CCWV) is a valid option with respect to other ensemble schemes and that because of their ability to balance diversity and accuracy, canonical views extracted using partially joint random view generation are more effective than those obtained by exploiting disjoint random view generation.

show abstract

“…Methods of the first group using feature representation transfer assume that the differences between domains can be mitigated by projecting both domains into a shared feature space in which the differences between the marginal feature distributions are minimized, e.g. by using feature selection (Gopalan et al, 2011) or feature extraction (Matasci et al, 2015). Some of the methods in this category are driven by a graph matching procedure to find correspondences between domains (Tuia et al, 2013;Banerjee et al, 2015).…”

Section: Related Workmentioning

confidence: 99%

“…Most research has therefore focussed on extending these metrics to multivariate data or to non-parametric models. Examples for such measures are the Kullback-Leibler Divergence (Sugiyama et al, 2007), the Total-Variation Distance (Sriperumbudur et al, 2012) and its approximations, the Maximum-Mean-Discrepancy Chattopadhyay et al, 2012;Matasci et al, 2015) and A-Distance (Ben-David et al, 2007). These approaches are kernel-based and usually scale well to high-dimensional data, but they may be computationally expensive.…”

Section: Related Workmentioning

confidence: 99%

Boosted Unsupervised Multi-Source Selection for Domain Adaptation

Vogt

Paul

Östermann

et al. 2017

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Supervised machine learning needs high quality, densely sampled and labelled training data. Transfer learning (TL) techniques have been devised to reduce this dependency by adapting classifiers trained on different, but related, (source) training data to new (target) data sets. A problem in TL is how to quantify the relatedness of a source quickly and robustly, because transferring knowledge from unrelated data can degrade the performance of a classifier. In this paper, we propose a method that can select a nearly optimal source from a large number of candidate sources. This operation depends only on the marginal probability distributions of the data, thus allowing the use of the often abundant unlabelled data. We extend this method to multi-source selection by optimizing a weighted combination of sources. The source weights are computed using a very fast boosting-like optimization scheme. The run-time complexity of our method scales linearly in regard to the number of candidate sources and the size of the training set and is thus applicable to very large data sets. We also propose a modification of an existing TL algorithm to handle multiple weighted training sets. Our method is evaluated on five survey regions. The experiments show that our source selection method is effective in discriminating between related and unrelated sources, almost always generating results within 3% in overall accuracy of a classifier based on fully labelled training data. We also show that using the selected source as training data for a TL method will additionally result in a performance improvement.

show abstract

Semisupervised Transfer Component Analysis for Domain Adaptation in Remote Sensing Image Classification

Cited by 191 publications

References 43 publications

Operational High Resolution Land Cover Map Production at the Country Scale Using Satellite Image Time Series

Operational High Resolution Land Cover Map Production at the Country Scale Using Satellite Image Time Series

Supervised and Semi-Supervised Multi-View Canonical Correlation Analysis Ensemble for Heterogeneous Domain Adaptation in Remote Sensing Image Classification

Boosted Unsupervised Multi-Source Selection for Domain Adaptation

Contact Info

Product

Resources

About